© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 14764
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the name "Hain" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ain"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     externalToEVAOnly
    -0.73
     mitigating
    -0.67
    illation
    -0.66
    nesday
    -0.64
    RNA
    -0.64
    RESULTS
    -0.64
    ILY
    -0.62
    odynamics
    -0.60
    odynam
    -0.60
    kefeller
    -0.58
    POSITIVE LOGITS
    thood
    1.23
    fo
    1.07
    tenance
    1.06
    esville
    1.06
    es
    1.01
    ese
    0.97
    bow
    0.97
    iae
    0.92
    ees
    0.91
    te
    0.89
    Activations Density 0.053%

    No Known Activations